Detection of Health Insurance Fraud using Bayesian Optimized XGBoost
Bibliographic record
Abstract
The mounting prevalence of health insurance fraud, propelled by a myriad of socioeconomic factors, presents significant hurdles to insurers, healthcare institutions, and individuals.In an attempt to counter this, insurance companies have begun harnessing the power of advanced technology, utilizing Machine Learning models to distinguish legitimate from fraudulent claims within expansive datasets.The present study conducts an in-depth examination of a health insurance dataset comprising 517,737 records, employing the Extreme Gradient Boosting (XGBoost) model as a potent tool for the detection of deceptive claims.In a noteworthy development, the performance of the model is markedly amplified through the integration of Bayesian optimization techniques, culminating in the Bayesian Optimized XGBoost (BOXGBoost) Model.The BOXGBoost Model is meticulously evaluated against an array of algorithms, which include Naive Bayes, Logistic Regression, Random Forest, K-Nearest Neighbor, and AdaBoost.A comparative analysis, focusing on key performance metrics such as accuracy, precision, recall, F1-Score, and the Area Under the Curve (AUC), is undertaken to discern the most effective algorithm.Remarkably, the proposed BOXGBoost model emerges as the superior performer, achieving an impressive accuracy rate of 98% and an AUC of 0.994.Additionally, the model exhibits high precision (98%), recall (97%), and F1-Score (97.5%), highlighting its exceptional capability in the prediction of health insurance fraud.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".